Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Probability questions with letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     releases
    -0.08
     Loved
    -0.07
     św
    -0.07
     every
    -0.07
    These
    -0.06
     koy
    -0.06
     districts
    -0.06
     Every
    -0.06
     dataList
    -0.06
    5
    -0.06
    POSITIVE LOGITS
    CppMethod
    0.07
     mMap
    0.06
    buquerque
    0.06
     поперед
    0.06
     Albuquerque
    0.06
    VEST
    0.06
    xffffff
    0.06
     Trading
    0.06
    .NumericUpDown
    0.06
    Precio
    0.06
    Act Density 0.002%

    No Known Activations